CN1259542C - Vision measuring method for spaced round geometrical parameters - Google Patents
Vision measuring method for spaced round geometrical parameters Download PDFInfo
- Publication number
- CN1259542C CN1259542C CNB03142659XA CN03142659A CN1259542C CN 1259542 C CN1259542 C CN 1259542C CN B03142659X A CNB03142659X A CN B03142659XA CN 03142659 A CN03142659 A CN 03142659A CN 1259542 C CN1259542 C CN 1259542C
- Authority
- CN
- China
- Prior art keywords
- image
- calibration
- camera
- point
- coordinate
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Expired - Fee Related
Links
Images
Landscapes
- Length Measuring Devices By Optical Means (AREA)
Abstract
The present invention belongs to the measurement technical field and relates to the improvement on a non-contact measuring method for the geometric parameters of a space round. The present invention is based on the non-contact high-accuracy simultaneous measurement method for a plurality of geometric parameters of a space round with a stereoscopic vision, utilizes a polar constraint for calculating the real three-dimensional space coordinates of the edge of a round, and adopts optimal fitting based on the space round for calculating the geometric parameters of the space round. The method of the present invention reduces the measurement error resulted from the distortion of the perspective projection shape of the space round and enhances the measuring accuracy of the geometric parameters of the round based on the visual method. When an angle between a plane on which a measured space round is positioned and a plane of a camera picture is more than 50 DEG, the 3 sigma repeatability accuracy measured at the geometric center of the space round is superior to +/-0.01mm.
Description
Technical field
The invention belongs to field of measuring technique, relate to improvement the geometric parameters of spatial circle non-contact measurement method.
Background technology
Circle is the basic geometric configuration of object, and as the pilot hole on various workpiece, the parts etc., the three-dimensional space position of the geometric center of these circular holes and the precision of radius of circle are to the successful installation of parts, and the integral body of object location, have great significance.General circular hole space geometry parameter can adopt three coordinate measuring machine to measure, the precision of three coordinate measuring machine can satisfy the measuring accuracy requirement of most of occasions to circle, but be subjected to the restriction in place, measurement can only be measured in the place that three coordinate measuring machine is installed, and can not satisfy the needs of the measurement of the especially large-scale circular hole in erecting stage.And vision detection technology is the new technology that has development potentiality in the precision measurement technical field most, its integrated use electronics, photodetection, Flame Image Process and computer technology, machine vision is incorporated in the industrial detection, realization is to the quick measurement of object (product or part) three-dimensional dimension or position, have noncontact, fast, the flexible good and high outstanding advantage of automaticity of speed, important application prospects is arranged in modern manufacturing industry.The Zhang Jianxin of University Of Tianjin's precision measurement measurement technology and instrument National Key Laboratory adopts and asks for circular hole center corresponding point based on ellipse fitting, directly measures the 3 d space coordinate at circular hole center.Referring to Zhang Jianxin work " applied research of technique of binocular stereoscopic vision in industrial detection ", University Of Tianjin's doctorate paper, 1996.This method obtains degree of precision in the ideal case.But when plane, circular hole place becomes than wide-angle with two planes of delineation of the sensor of forming stereoscopic vision, because there is shape distortion in the circle perspective projection, adopt this method to exist, and do not realize the measurement of the normal vector on radius of circle and plane, circle place than mistake.
Summary of the invention
Technical matters to be solved by this invention is: the contactless high-precision stereo vision measurement method that the many geometric parameters of a kind of space circle (normal vector that comprises center of circle three-dimensional coordinate, radius of circle and plane, circle place) is provided, reduce the influence of plane, measured circle place and mutual alignment, camera review plane to measuring accuracy, widen the range of application that stereoscopic vision is measured, improve the automaticity of space circle measurement means.
Technical solution of the present invention is: a kind of many geometric parameters of space circle contactless high-precision stereo vision measurement method, it is characterized in that measuring process is divided into calibration phase and measuring phases, but continuous coverage after once demarcating, concrete steps are as follows:
1, calibration phase:
1.1, set target, target is a two dimensional surface, and the unique point that sets in advance is arranged on the target surface, the target face is one of following structure:
A, target first, on the target plane, be covered with chequered with black and white gridiron pattern, the length of side of black and white square is (3～50) mm, its length of side precision is (0.001～0.01) mm, the publicly-owned summit of black box and white square is called lattice point, choose that lattice point is as feature point for calibration on the target surface, the quantity of unique point is 16～400;
B, target second, the black square that arranged is arranged on the target plane, square quantity is 4～100, the length of side of square is (3～50) mm, its length of side precision is (0.001～0.01) mm, the square spacing is 3～50mm, and its spacing precision is (0.001～0.01) mm, and the summit of choosing each square is a unique point;
1.2, fix the binocular tri-dimensional sense sensor of forming by left video camera and right video camera, open the power supply of two ccd video cameras of stereo vision sensor;
1.3, in the public view field scope of two video cameras, free, at least 5 positions of non-parallel ground moving target mark, whenever move a position, left side video camera, right video camera are taken piece image respectively and are stored computing machine into, the feature point for calibration of target should be included in the image, the image that left side video camera is taken is called left camera calibration image, and the image that right video camera is taken is called right camera calibration image;
1.4, extract the image coordinate of feature point for calibration in all left camera calibration images, these coordinates are called left camera calibration unique point image coordinate, extract the image coordinate of feature point for calibration in all right camera calibration images, these coordinates are called right camera calibration unique point image coordinate, with all left camera calibration unique point image coordinate with and corresponding right camera calibration unique point image coordinate and world coordinates store in the computing machine;
1.5, utilize left camera calibration unique point image coordinate and corresponding world coordinate to demarcate left intrinsic parameters of the camera and store in the computing machine;
1.6, utilize right camera calibration unique point image coordinate and corresponding world coordinate to demarcate right intrinsic parameters of the camera and store in the computing machine;
1.7, according to the left and right cameras inner parameter of demarcating, calculate the normalized image coordinate of left and right sides feature point for calibration respectively;
1.8, utilize corresponding left and right cameras feature point for calibration normalized image coordinate, obtain the essential matrix and the structural parameters of binocular vision sensor and store in the computing machine;
2, measuring phases:
2.1, tested circular hole is placed in the measurement space of binocular tri-dimensional sense sensor;
2.2, gather the image that comprises the same space circle respectively by left and right cameras, left camera acquisition be called left video camera measurement image, right camera acquisition be called right video camera measurement image;
2.3, according to the distortion model of left and right cameras, proofread and correct the distortion of left and right cameras measurement image respectively, obtain undistorted left and right video camera measurement image;
2.4, in undistorted left and right video camera measurement image, adopt image processing algorithm, visit automatically respectively and take out left and right cameras projection ellipse, and fitted ellipse, storage basic model parameter is in computing machine;
2.5, chose respectively 20～100 equally distributed polar curves crossing two elliptical center, guarantees that every polar curve and oval image border meet at 2 points, retrain and the sequence consensus principle by polar curve, set up the corresponding matching relationship of every pair of edge corresponding point;
2.6, according to the corresponding match point in the edge built, stereo vision three-dimensional measurement model by point, obtain the three dimensional space coordinate of space circle marginal point, the match space circle is obtained the normal vector on the geometric center, radius of space circle and plane, circle place and is stored in the computing machine by the space circle of match.
Advantage of the present invention is: the contactless high-precision that this method provides a kind of many geometric parameters of space circle based on stereoscopic vision is measuring method simultaneously, utilize the polar curve constraint to obtain the actual three dimensional space coordinate of rounded edge, adopt and ask for geometric parameters of spatial circle based on the space circle optimal fitting.This method has reduced the measuring error that space circle perspective projection shape distortion causes, has improved the measuring accuracy based on the circle geometric parameter of visible sensation method.Angled during greater than 50 ° when detected space circle plane, place and camera review plane, 3 σ repeatability precisions of spacing circle geometric center measurement are better than ± 0.01mm.This method has reduced the influence to measuring accuracy of plane, measured circle place and mutual alignment, camera review plane, has widened the range of application that stereoscopic vision is measured, and has improved the automaticity of space circle measurement means.
Description of drawings
Fig. 1 is the plane target drone synoptic diagram.
Fig. 2 is a binocular tri-dimensional sense sensor mathematical model.
Fig. 3 is the left measurement image that adopts the space circle that stereo vision sensor obtains.
Fig. 4 is the right measurement image that adopts the space circle that stereo vision sensor obtains.
Fig. 5 is the tested edge in the left measurement image.
Fig. 6 is the tested edge in the right measurement image.
Fig. 7 is the image coordinate of the tested marginal point in the left measurement image.
Fig. 8 is the image coordinate of the tested marginal point in the right measurement image.
Fig. 9 is the three dimensional space coordinate of rounded edge.
Embodiment
Below the inventive method is described in further details.The contactless high-precision that the invention provides a kind of many geometric parameters of space circle based on stereoscopic vision is measuring method simultaneously, utilizes the polar curve constraint to obtain the actual three dimensional space coordinate of rounded edge, adopts and asks for geometric parameters of spatial circle based on the space circle optimal fitting.
The stereoscopic vision measurement model of the 3 d space coordinate of point.
Spatial point three-dimensional measurement The Mathmatic Models of Instrument Transducers of being made up of two video cameras and corresponding various coordinate system are as shown in Figure 2.Suppose that left video camera three-dimensional coordinate is oXYZ, image coordinate is O
LRX
LRY
LRRight video camera three-dimensional coordinate is o
RcX
RcY
RcZ
Rc, image coordinate is o
RRX
RRY
RRSensor coordinate system is consistent with left camera coordinate system.
The inner parameter matrix of two video cameras is:
(f
Lx, f
Ly) be left video camera at x, the effective focal length of y direction, (u
L0, v
L0) be left video camera principal point coordinate.(f
Rx, f
Ry) be right video camera at x, the effective focal length of y direction, (u
R0, v
R0) be right video camera principal point coordinate.If the homogeneous image coordinate of left video camera of any 1 P in space is x
L1=(x
L1, y
L1, 1)
T, the normalization coordinate is x
Nl=(x
Nl, y
Nl, 1)
T, the homogeneous image coordinate of right video camera is x
Rl=(x
Rl, y
Rl, 1)
T, the normalization coordinate is x
Nr=(x
Nr, y
Nr, 1)
T, then have:
Obtain by perspective projection:
Sensor measurement coordinate system oXYZ (left camera coordinate system) and right camera coordinate system o
RcX
RcY
RcZ
RcBetween euclidean transformation can be expressed as by 3 * 4 matrix M:
Three dimensional space coordinate vision measurement mathematical model then can be expressed as:
The inner parameter of known two video cameras, and obtain spatial point corresponding image coordinate in left and right cameras by Flame Image Process, just can obtain the three dimensional space coordinate of testee point according to formula (4).
According to the binocular stereo vision The Mathmatic Models of Instrument Transducers, the measurement space circle is divided into two stages: the demarcation of sensor parameters and measure two stages according to model.
The concrete steps of the inventive method are as follows:
Calibration phase:
1, set target, target is a two dimensional surface, and the unique point that sets in advance is arranged on the target surface, and the target face is one of following structure:
A, target first are covered with chequered with black and white gridiron pattern on the target plane, the length of side of black and white square is (3～50) mm, and its length of side precision is (0.001～0.01) mm, and the publicly-owned summit of black box and white square is called lattice point.Choose that lattice point is as feature point for calibration on the target surface, the quantity of unique point is 16～400;
B, target second, the black square that arranged is arranged on the target plane, square quantity is 4～100, the length of side of square is (3～50) mm, its length of side precision is (0.001～0.01) mm, the square spacing is 3～50mm, and its spacing precision is (0.001～0.01) mm, and the summit of choosing each square is a unique point;
2, fix the binocular tri-dimensional sense sensor of forming by left video camera and right video camera, open the power supply of two ccd video cameras of stereo vision sensor.
3, in the public view field scope of two video cameras, freely, at least 5 positions of plane of motion target, non-parallel ground.So-called non-parallel, promptly the target of two positions has certain windup-degree.Whenever move a position, left video camera, right video camera are taken piece image respectively, the image of taking is called left camera calibration image and right camera calibration image, and stores image into computing machine.Require the unique point of plane target drone to be included in the image.
4, extract the image coordinate of unique point in all left camera calibration images, be referred to as left camera calibration unique point image coordinate.Extract the image coordinate of unique point in all right camera calibration images simultaneously, be referred to as right camera calibration unique point image coordinate.With all left camera calibration unique point image coordinate with and corresponding right camera calibration unique point image coordinate and world coordinates store in the computing machine.The automatic extraction algorithm of feature point for calibration image coordinate is referring to Zhou Fuqiang work " the gordian technique research that binocular stereo vision detects ", BJ University of Aeronautics ﹠ Astronautics's post-doctoral research work report, 2002.
5, utilize left camera calibration unique point image coordinate and corresponding world coordinate to demarcate left intrinsic parameters of the camera (effective focal length, principal point and the distortion factor that comprise left video camera) and store in the computing machine.Calibration algorithm is referring to Zhou Fuqiang work " the gordian technique research that binocular stereo vision detects ", BJ University of Aeronautics ﹠ Astronautics's post-doctoral research work report, 2002.
6, utilize right camera calibration unique point image coordinate and corresponding world coordinate to demarcate right intrinsic parameters of the camera (effective focal length, principal point and the distortion factor that comprise right video camera) and store in the computing machine.Calibration algorithm is identical with 5.
7,, calculate the normalized image coordinate of left and right sides feature point for calibration respectively according to formula (1) according to the left and right cameras inner parameter of demarcating.
8, utilize corresponding left and right cameras feature point for calibration normalized image coordinate, obtain the essential matrix and the structural parameters of binocular vision sensor and store in the computing machine.Ask the algorithm and the calibration structure parameter algorithm of essential matrix to show " the gordian technique research that binocular stereo vision detects ", BJ University of Aeronautics ﹠ Astronautics's post-doctoral research work report, 2002 referring to Zhou Fuqiang.
Finish after the demarcation,, can carry out continuous coverage different measuring objects as long as do not adjust the camera lens and the aperture of left and right cameras and do not change two relative positions between the video camera.
Measuring phases:
9, tested circular hole is placed in the measurement space of binocular tri-dimensional sense sensor.
10, gather the image that comprises the same space circle respectively by left and right video camera, be called left and right video camera measurement image.
11, according to the left and right cameras distortion model, proofread and correct the distortion of left and right cameras measurement image respectively, obtain undistorted left and right video camera measurement image.The distortion correction algorithm is referring to Zhou Fuqiang work " the gordian technique research that binocular stereo vision detects ", BJ University of Aeronautics ﹠ Astronautics's post-doctoral research work report, 2002.
12, in undistorted left and right video camera measurement image, adopt image processing algorithm, visit automatically respectively and take out left and right video camera projection ellipse, and fitted ellipse, storage basic model parameter is in computing machine.Oval extraction algorithm automatically is referring to Zhou Fuqiang work " the gordian technique research that binocular stereo vision detects ", BJ University of Aeronautics ﹠ Astronautics's post-doctoral research work report, 2002.
13, choose 20～100 equally distributed polar curves crossing two elliptical center respectively, guarantee that every polar curve and oval image border meet at 2 points,, set up the corresponding matching relationship of every pair of edge corresponding point by polar curve constraint and sequence consensus principle.The algorithm of asking for corresponding point is referring to Zhou Fuqiang work " the gordian technique research that binocular stereo vision detects ", BJ University of Aeronautics ﹠ Astronautics's post-doctoral research work report, 2002.
14, according to the corresponding match point in the edge of being built, stereo vision three-dimensional measurement model by point, obtain the three dimensional space coordinate of space circle marginal point, the match space circle is obtained the normal vector on the geometric center, radius of space circle and plane, circle place and is stored in the computing machine by the space circle of match.Three dimensions circle nonlinear optimization fitting algorithm is referring to the article " the least square fitting algorithm of NIST (National Institute of Standards and Technology) test of heuristics system " [Least-Squares Fitting Algorithms of the NIST Algorithm TestingSystem] of Craig M.Shakarji, NIST studies periodical, the 103rd the 6th phase of volume, the 633rd～641 page, November～Dec, 1998.[Journal?of?Research?of?the?National?Institute?of?Standardsand?Technology，Vol.103，No.6，1998]。Nonlinear optimization method is chosen the Levenberg-Marquardt algorithm, and its initial value choosing method is: the central coordinate of circle of space circle is the barycenter at all number of edges strong points; Radius of a circle is the mean distance of barycenter to the edge; The direction cosine on the plane at circle place are tried to achieve by the least square plane match in the three dimensions at all number of edges strong points.Checking by experiment, this initial value system of selection is quite rational, it can guarantee the computing velocity and the convergence of optimizing process.After utilizing stereoscopic vision to obtain the marginal point volume coordinate,, just can measure the geometric parameter of space circle by the space circle optimal fitting.The Levenberg-Marquardt algorithm, referring to " Optimum Theory and method ", (Yuan Yaxiang, Sun Wenyu work, Science Press, 1999).
Embodiment
According to the step of narrating above, form a binocular tri-dimensional sense sensor with two quick logical 368P ccd video cameras, 25mm NSK camera lens, the circular hole that a diameter is D=45.50mm is measured.At first utilize plane reference target shown in Figure 1 that ccd video camera and structured light vision sensor are demarcated, the spacing of adjacent feature point is 9 ± 0.005mm in the plane target drone.The calibrating parameters that obtains is:
Left side intrinsic parameters of the camera:
Left side distortion of camera coefficient is:
(k
1，k
2，p
1，p
2)＝(-3.579658×10
-1，1.941033×10
1，1.911845×10
-4-2.724081×10
-2)
Right intrinsic parameters of the camera:
Right distortion of camera coefficient is:
(k
1，k
2，p
1，p
2)＝(2.390095×10
-1，-7.079636×10
0，5.048423×10
-3?1.410062×10
-3)
Essential matrix is:
The sensor construction parameter: rotation matrix is
Translation vector be T=(57.453-432.348-134.136)
T
RMS (the measuring 62 points) error of 2 distances of binocular stereo vision sensor measurement object space of demarcating is: E
RMS=0.023mm.
Fig. 3,4 is respectively the two round width of cloth stereo-pictures of the same space that adopt stereo vision sensor to obtain.Fig. 5,6 is the edge corresponding point of being set up.After obtaining the edge corresponding point, utilize the marginal point volume coordinate that stereoscopic vision obtains after, behind the space circle optimal fitting, just can measure the geometric parameter of circular hole.The image coordinate of the part edge point of measuring is shown in Fig. 7,8, and the three dimensional space coordinate of rounded edge as shown in Figure 9.The plane, circular hole place in the experiment and the plane of delineation of video camera are into about 50 ° angle, and the space circle parameter of measurement is:
Central coordinate of circle: (1.5949.972-713.863) mm
The normal vector on plane, circle place: (0.213-0.343-0.915)
Radius of circle: r=22.778mm differs 0.028mm with the circle real radius.
Claims (1)
1, a kind of many geometric parameters of space circle contactless high-precision stereo vision measurement method is characterized in that measuring process is divided into calibration phase and measuring phases, but continuous coverage after once demarcating, and concrete steps are as follows:
1.1, calibration phase:
1.1.1, set target, target is a two dimensional surface, and the unique point that sets in advance is arranged on the target surface, the target face is one of following structure:
A, target first, on the target plane, be covered with chequered with black and white gridiron pattern, the length of side of black and white square is 3～50mm, its length of side precision is 0.001～0.01mm, the publicly-owned summit of black box and white square is called lattice point, choose that lattice point is as feature point for calibration on the target surface, the quantity of unique point is 16～400;
B, target second have into the black square of arranged on the target plane, square quantity is 4～100, the length of side 3～the 50mm of square, its length of side precision is 0.001～0.01mm, the square spacing is 3～50mm, its spacing precision 0.001～0.01mm, the summit of choosing each square is a unique point;
1.1.2, fix the binocular tri-dimensional sense sensor of forming by left video camera and right video camera, open the power supply of two ccd video cameras of stereo vision sensor;
1.1.3, in the public view field scope of two video cameras, free, at least 5 positions of non-parallel ground moving target mark, whenever move a position, left side video camera, right video camera are taken piece image respectively and are stored computing machine into, the feature point for calibration of target should be included in the image, the image that left side video camera is taken is called left camera calibration image, and the image that right video camera is taken is called right camera calibration image;
1.1.4, extract the image coordinate of feature point for calibration in all left camera calibration images, these coordinates are called left camera calibration unique point image coordinate, extract the image coordinate of feature point for calibration in all right camera calibration images, these coordinates are called right camera calibration unique point image coordinate, with all left camera calibration unique point image coordinate with and corresponding right camera calibration unique point image coordinate and world coordinates store in the computing machine;
1.1.5, utilize left camera calibration unique point image coordinate and corresponding world coordinate to demarcate left intrinsic parameters of the camera and store in the computing machine;
1.1.6, utilize right camera calibration unique point image coordinate and corresponding world coordinate to demarcate right intrinsic parameters of the camera and store in the computing machine;
1.1.7, according to the left and right cameras inner parameter of demarcating, calculate the normalized image coordinate of left and right sides feature point for calibration respectively;
1.1.8, utilize corresponding left and right cameras feature point for calibration normalized image coordinate, obtain the essential matrix and the structural parameters of binocular vision sensor and store in the computing machine;
1.2, measuring phases:
1.2.1, tested circular hole is placed in the measurement space of binocular tri-dimensional sense sensor;
1.2.2, gather the image that comprises the same space circle respectively by left and right cameras, left camera acquisition be called left video camera measurement image, right camera acquisition be called right video camera measurement image;
1.2.3, according to the distortion model of left and right cameras, proofread and correct the distortion of left and right cameras measurement image respectively, obtain undistorted left and right video camera measurement image;
1.2.4, in undistorted left and right video camera measurement image, adopt image processing algorithm, visit automatically respectively and take out left and right cameras projection ellipse, and fitted ellipse, storage basic model parameter is in computing machine;
1.2.5, chose respectively 20～100 equally distributed polar curves crossing two elliptical center, guarantees that every polar curve and oval image border meet at 2 points, retrain and the sequence consensus principle by polar curve, set up the corresponding matching relationship of every pair of edge corresponding point;
1.2.6, according to the corresponding match point in the edge built, stereo vision three-dimensional measurement model by point, obtain the three dimensional space coordinate of space circle marginal point, the match space circle is obtained the normal vector on the geometric center, radius of space circle and plane, circle place and is stored in the computing machine by the space circle of match.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CNB03142659XA CN1259542C (en) | 2003-06-11 | 2003-06-11 | Vision measuring method for spaced round geometrical parameters |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CNB03142659XA CN1259542C (en) | 2003-06-11 | 2003-06-11 | Vision measuring method for spaced round geometrical parameters |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN1566900A CN1566900A (en) | 2005-01-19 |
| CN1259542C true CN1259542C (en) | 2006-06-14 |
Family
ID=34471155
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CNB03142659XA Expired - Fee Related CN1259542C (en) | 2003-06-11 | 2003-06-11 | Vision measuring method for spaced round geometrical parameters |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN1259542C (en) |
Families Citing this family (37)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP4833588B2 (en) * | 2005-06-03 | 2011-12-07 | 株式会社ミツトヨ | Image measurement system and non-stop image measurement program creation method and execution method |
| EP1898358A1 (en) * | 2006-09-05 | 2008-03-12 | Research In Motion Limited | SVG script editor |
| CN100429476C (en) * | 2006-12-20 | 2008-10-29 | 北京航空航天大学 | Double-sensor laser visual measuring system calibrating method |
| CN100491903C (en) * | 2007-09-05 | 2009-05-27 | 北京航空航天大学 | Method for calibrating structural parameter of structure optical vision sensor |
| CN101377405B (en) * | 2008-07-11 | 2010-04-14 | 北京航空航天大学 | Vision measuring method of space round gesture parameter and geometric parameter |
| CN101377404B (en) * | 2008-07-11 | 2010-04-14 | 北京航空航天大学 | Method for disambiguating space round gesture recognition ambiguity based on angle restriction |
| CN101419709B (en) * | 2008-12-08 | 2012-07-18 | 北京航空航天大学 | Plane target drone characteristic point automatic matching method for demarcating video camera |
| CN101699219B (en) * | 2009-10-30 | 2011-01-26 | 北京理工大学 | Method and sensor for binocular vision 3D measurement |
| CN101876533B (en) | 2010-06-23 | 2011-11-30 | 北京航空航天大学 | Microscopic stereovision calibrating method |
| CN102313515B (en) * | 2010-07-08 | 2013-10-23 | 国立清华大学 | Three-dimensional digital image correlation (3D-DIC) correcting method |
| CN102012217B (en) * | 2010-10-19 | 2012-07-04 | 南京大学 | Method for measuring three-dimensional geometrical outline of large-size appearance object based on binocular vision |
| CN102353340B (en) * | 2011-06-08 | 2013-08-28 | 天津大学 | Cylinder-cover blank machining-size identifying method and device |
| CN102288115B (en) * | 2011-07-11 | 2013-04-17 | 南京信息工程大学 | Method for precisely measuring roller geometric dimension on line |
| CN102519434B (en) * | 2011-12-08 | 2014-04-02 | 北京控制工程研究所 | Test verification method for measuring precision of stereoscopic vision three-dimensional recovery data |
| CN102944191B (en) * | 2012-11-28 | 2015-06-10 | 北京航空航天大学 | Method and device for three-dimensional vision measurement data registration based on planar circle target |
| CN104173054B (en) * | 2013-05-21 | 2017-04-12 | 杭州海康威视数字技术股份有限公司 | Measuring method and measuring device for height of human body based on binocular vision technique |
| CN103308000B (en) * | 2013-06-19 | 2015-11-18 | 武汉理工大学 | Based on the curve object measuring method of binocular vision |
| CN103400377B (en) * | 2013-07-22 | 2016-04-20 | 上海理工大学 | A kind of three-dimensional circular target based on binocular stereo vision detects and determination methods |
| CN104330041A (en) * | 2014-09-30 | 2015-02-04 | 中铁山桥集团有限公司 | Measuring method for track switch steel rail member drill hole dimension |
| CN105627917A (en) * | 2014-11-05 | 2016-06-01 | 北京航天计量测试技术研究所 | Large-scale structural component assembly joining measurement method based on visual principle |
| CN107230227B (en) * | 2017-06-02 | 2020-11-03 | 华中科技大学无锡研究院 | Ellipse conformation deviation estimation method based on tangent method |
| CN107220999A (en) * | 2017-06-19 | 2017-09-29 | 江南大学 | The research of workpiece circular arc Edge Feature Points matching process |
| CN107270826B (en) * | 2017-06-29 | 2019-11-22 | 西安理工大学 | A kind of vision measuring method in hole |
| CN108038878B (en) * | 2017-11-07 | 2021-02-12 | 武汉中观自动化科技有限公司 | Method and system for determining normal direction and radius of mark point in photogrammetry |
| CN108509908B (en) * | 2018-03-31 | 2022-05-17 | 天津大学 | Pupil diameter real-time measurement method based on binocular stereo vision |
| CN108871228B (en) * | 2018-05-11 | 2019-11-22 | 天津大学 | Binocular vision circular feature geometric parameter estimation method based on geometrical constraint |
| CN108765495B (en) * | 2018-05-22 | 2021-04-30 | 山东大学 | Rapid calibration method and system based on binocular vision detection technology |
| CN109163657B (en) * | 2018-06-26 | 2020-04-10 | 浙江大学 | Round target pose detection method based on binocular vision three-dimensional reconstruction |
| CN109000572B (en) * | 2018-09-17 | 2019-09-10 | 四川大学 | A kind of body diameter detection method |
| CN109470170B (en) * | 2018-12-25 | 2020-01-07 | 山东大学 | Stereoscopic vision space circular attitude high-precision measurement method and system based on optimal projection plane |
| CN111380474A (en) * | 2018-12-29 | 2020-07-07 | 北京伟景智能科技有限公司 | Aperture detection method based on binocular vision |
| CN109855566B (en) * | 2019-02-28 | 2021-12-03 | 易思维（杭州）科技有限公司 | Method for extracting slot features |
| CN109974608B (en) * | 2019-03-18 | 2020-11-03 | 吉林大学 | Part aperture size measuring method based on machine vision technology |
| CN110763140B (en) * | 2019-07-08 | 2021-04-16 | 北京宇航时代科技发展有限公司 | Non-parallel optical axis high-precision binocular ranging method |
| CN111121655B (en) * | 2019-12-18 | 2021-01-19 | 浙江大学 | Visual detection method for pose and aperture of coplanar workpiece with equal large hole patterns |
| CN111551920A (en) * | 2020-04-16 | 2020-08-18 | 重庆大学 | Three-dimensional target real-time measurement system and method based on target detection and binocular matching |
| CN114608465B (en) * | 2022-03-01 | 2024-04-12 | 浙江工业大学 | Computer vision-based real-time measurement method for spatial displacement of multiple measuring points of civil engineering structure |
-
2003
- 2003-06-11 CN CNB03142659XA patent/CN1259542C/en not_active Expired - Fee Related
Also Published As
| Publication number | Publication date |
|---|---|
| CN1566900A (en) | 2005-01-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN1259542C (en) | Vision measuring method for spaced round geometrical parameters | |
| CN1250942C (en) | Construction optical visual sense transducer calibration method based on plane targets | |
| CN102364299B (en) | Calibration technology for multiple structured light projected three-dimensional profile measuring heads | |
| CN1259543C (en) | Laser vision on-line automatic measuring method for tire multiple geometrical parameters | |
| CN105716542B (en) | A kind of three-dimensional data joining method based on flexible characteristic point | |
| CN1975324A (en) | Double-sensor laser visual measuring system calibrating method | |
| CN103236076B (en) | Based on the three-dimensional object model reconstruction system and method for laser image | |
| CN101629806B (en) | Nonlinear CCD 3D locating device combined with laser transmitter and locating method thereof | |
| CN109579695B (en) | Part measuring method based on heterogeneous stereoscopic vision | |
| CN108507462B (en) | A kind of scaling method of four axis measuring device rotary shaft of holographic interference | |
| CN109242915A (en) | Multicamera system scaling method based on multi-face solid target | |
| CN101074869A (en) | Method for measuring three-dimensional contour based on phase method | |
| CN104567728A (en) | Laser vision profile measurement system, measurement method and three-dimensional target | |
| CN102221331B (en) | Measuring method based on asymmetric binocular stereovision technology | |
| CN104034305B (en) | A kind of monocular vision is the method for location in real time | |
| CN105115560B (en) | A kind of non-contact measurement method of cabin volume of compartment | |
| CN1888814A (en) | Multi-viewpoint attitude estimating and self-calibrating method for three-dimensional active vision sensor | |
| CN101377405B (en) | Vision measuring method of space round gesture parameter and geometric parameter | |
| CN110378969A (en) | A kind of convergence type binocular camera scaling method based on 3D geometrical constraint | |
| CN109272555B (en) | External parameter obtaining and calibrating method for RGB-D camera | |
| WO2022111105A1 (en) | Intelligent visual 3d information acquisition apparatus with free posture | |
| CN103735282A (en) | Device and method for geometric correction of detector of cone-beam CT (computed tomography) system | |
| CN105157592A (en) | Binocular vision-based method for measuring deformation shape and deformation rate of flexible trailing edge of adaptive wing | |
| CN113205603A (en) | Three-dimensional point cloud splicing reconstruction method based on rotating platform | |
| CN103106661A (en) | Solving parabolic catadioptric camera parameters through two intersected straight lines in space |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| ASS | Succession or assignment of patent right |
Owner name: BEIJING ZHONGZI BANGKE TECHNOLOGY CO., LTD. Free format text: FORMER OWNER: BEIJING UNIV. OF AERONAUTICS + ASTRONAUTICS Effective date: 20100406 |
|
| C41 | Transfer of patent application or patent right or utility model | ||
| COR | Change of bibliographic data |
Free format text: CORRECT: ADDRESS; FROM: 100083 NO.37,XUYUAN ROAD, BEIJING CITY TO: 100080 ROOM 618, YINGU BUILDING,NO.9, NORTH 4TH RING WEST ROAD, HAIDIAN DISTRICT, BEIJING CITY |
|
| TR01 | Transfer of patent right |
Effective date of registration: 20100406 Address after: 100080 Beijing city Haidian District North Fourth Ring Road No. nine Yingu building room 618 Patentee after: Beijing self Bangke Technology Co. Ltd. Address before: 100083 No. 37, Beijing, Xueyuan Road Patentee before: Beihang University |
|
| ASS | Succession or assignment of patent right |
Owner name: HUANGSHI CITY BANGKE TECHNOLOGY CO., LTD. Free format text: FORMER OWNER: BEIJING ZHONGZI BANGKE TECHNOLOGY CO., LTD. Effective date: 20100813 |
|
| C41 | Transfer of patent application or patent right or utility model | ||
| COR | Change of bibliographic data |
Free format text: CORRECT: ADDRESS; FROM: 100080 ROOM 618, YINGU BUILDING, NO.9, NORTH 4TH RING WEST ROAD, HAIDIAN DISTRICT, BEIJING CITY TO: 435000 NO.189, HANGZHOU ROAD, HUANGSHI CITY, HUBEI PROVINCE |
|
| TR01 | Transfer of patent right |
Effective date of registration: 20100813 Address after: 435000 No. 189, Hangzhou Road, Huangshi, Hubei Patentee after: Huangshi City Bangke Technology Co., Ltd. Address before: 100080 Beijing city Haidian District North Fourth Ring Road No. nine Yingu building room 618 Patentee before: Beijing self Bangke Technology Co. Ltd. |
|
| C56 | Change in the name or address of the patentee | ||
| CP01 | Change in the name or title of a patent holder |
Address after: 435000 No. 189, Hangzhou Road, Huangshi, Hubei Patentee after: Huangshi Bangke Technology Co., Ltd. Address before: 435000 No. 189, Hangzhou Road, Huangshi, Hubei Patentee before: Huangshi City Bangke Technology Co., Ltd. |
|
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20060614 Termination date: 20150611 |
|
| EXPY | Termination of patent right or utility model |